Search

Responses to the COVID‐19 pandemic led to major reductions on air pollutant emissions in modern history. To date, there has been no comprehensive assessment for the impact of lockdowns on the vertical distributions of nitrogen dioxide (NO2) and formaldehyde (HCHO). Based on profiles from 0 to 2 km retrieved by Multi‐AXis‐Differential Optical Absorption Spectroscopy observation and a large volume of real‐time data at a suburb site in Shanghai, China, four types of machine learning models were developed and compared, including multiple linear regression, support vector machine, bagged trees (BT), and artificial neural network. Ultimately BT model was employed to reproduce NO2and HCHO profiles with the best performance. Predictions with different meteorological and surface pollution scenarios were conducted from 2017 to 2019, for assessing the corresponding impacts on the changes of NO2and HCHO profiles during COVID‐19 lockdown. The simulations illustrate that the NO2decreased in 2020 by 43.8%, 45.5%, and 44.6%, relative to 2017, 2018, and 2019, respectively. For HCHO, the lockdown‐induced situation presented the declines of 28.6%, 32.1%, and 10.9%, respectively. In the comparisons of vertical distributions, NO2maintained decreasing at all altitudes, while HCHO decreased at low altitudes and increased at high altitudes. During COVID‐19 lockdown, the reduction of NO2and HCHO from the variation of surface pollutants was dominated below 0.5 km, while the relevant meteorological factors played a more significant role above 0.5 km. This study evaluated the impact of COVID‐19 lockdown on the vertical distributions of NO2and HCHO by developing the machine‐learning (ML) air pollution prediction models. The ML model allows us to quantify the timing and magnitude influencing real‐world air quality responses to surface pollution scenarios and meteorological factors. Compared with the simulations for vertical profiles in the normal scenarios, it can be found that NO2maintained decreasing at all altitudes, while HCHO decreased at low altitudes and increased at high altitudes. In addition, the lockdown‐induced NO2and HCHO were mainly driven by meteorological factors and surface pollutants above and below 0.5 km, respectively. The machine learning model was applied to reproduce NO2and HCHO profiles for the first timeQualifying the vertical distribution of reductions during COVID‐19 lockdown relative to the normal scenarioThe lockdown‐induced NO2and HCHO were mainly driven by meteorological factors and surface pollutants above and below 0.5 km, respectively The machine learning model was applied to reproduce NO2and HCHO profiles for the first time Qualifying the vertical distribution of reductions during COVID‐19 lockdown relative to the normal scenario The lockdown‐induced NO2and HCHO were mainly driven by meteorological factors and surface pollutants above and below 0.5 km, respectively